Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations
2
Citation
61
Reference
20
Related Paper
Citation Trend
Abstract:
Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this paper, we first study how biases in the dataset affect existing methods. Our results show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets. Second, given the generality of the approach, we try to realize further gains with minor modifications. We show that learning additional invariances -- through the use of multi-scale cropping, stronger augmentations and nearest neighbors -- improves the representations. Finally, we observe that MoCo learns spatially structured representations when trained with a multi-crop strategy. The representations can be used for semantic segment retrieval and video instance segmentation without finetuning. Moreover, the results are on par with specialized models. We hope this work will serve as a useful study for other researchers. The code and models will be available at this https URL.Keywords:
Generality
Code (set theory)
Cite
Unsupervised person re-identification (ReID) aims at learning discriminative identity features without annotations. Recently, self-supervised contrastive learning has gained increasing attention for its effectiveness in unsupervised representation learning. The main idea of instance contrastive learning is to match a same instance in different augmented views. However, the relationship between different instances has not been fully explored in previous contrastive methods, especially for instance-level contrastive loss. To address this issue, we propose Inter-instance Contrastive Encoding (ICE) that leverages inter-instance pairwise similarity scores to boost previous class-level contrastive ReID methods. We first use pairwise similarity ranking as one-hot hard pseudo labels for hard instance contrast, which aims at reducing intra-class variance. Then, we use similarity scores as soft pseudo labels to enhance the consistency between augmented and original views, which makes our model more robust to augmentation perturbations. Experiments on several large-scale person ReID datasets validate the effectiveness of our proposed unsupervised method ICE, which is competitive with even supervised methods. Code is made available at https://github.com/chenhao2345/ICE.
Discriminative model
Similarity (geometry)
Identification
Cite
Citations (0)
Due to the high (human) cost of image annotation, lack of large-scale annotation data prevents computer vision models from fully solving image classification tasks. On the other hand, the Bert model [1] has shown that training large scale models with non-annotation text data is possible. Inspired by this, we propose a Self-supervised Visual Feature Learning and Classification framework (SVFLC) that can be applied to large scale training data without annotation. This approach is based on the contrastive predictive learning (CPL) method. By refining CPL using special data augmentation and new contrastive learning mechanisms, learning shape-biased features can be emphasized. In the next step, these features are used to produce pseudo labels via a clustering algorithm. Inspired by the recent research on noisy labels, we proceed to employ distance of the sample from cluster centers to eliminate low-confidence labels, and use soft triplet loss and classification loss jointly for achieving robust performance in the final classification. In this unsupervised learning paradigm, on the Imagenet dataset, our framework outperforms commonly used approaches. The unsupervised performance is lower than supervised and semi-supervised learning approaches, but our proposed framework is more suitable for general cases, and serves as a baseline algorithm for future improvement to the unsupervised learning paradigm.
Feature (linguistics)
Supervised Learning
Feature Learning
Contextual image classification
Cite
Citations (1)
Labeling videos at scale is impractical. Consequently, self-supervised visual representation learning is key for efficient video analysis. Recent success in learning image representations suggests contrastive learning is a promising framework to tackle this challenge. However, when applied to real-world videos, contrastive learning may unknowingly lead to the separation of instances that contain semantically similar events. In our work, we introduce a cooperative variant of contrastive learning to utilize complementary information across views and address this issue. We use data-driven sampling to leverage implicit relationships between multiple input video views, whether observed (e.g. RGB) or inferred (e.g. flow, segmentation masks, poses). We are one of the firsts to explore exploiting inter-instance relationships to drive learning. We experimentally evaluate our representations on the downstream task of action recognition. Our method achieves competitive performance on standard benchmarks (UCF101, HMDB51, Kinetics400). Furthermore, qualitative experiments illustrate that our models can capture higher-order class relationships.
Leverage (statistics)
Feature Learning
Representation
Cite
Citations (0)
Learning robust representations to discriminate cell phenotypes based on microscopy images is important for drug discovery. Drug development efforts typically analyse thousands of cell images to screen for potential treatments. Early works focus on creating hand-engineered features from these images or learn such features with deep neural networks in a fully or weakly-supervised framework. Both require prior knowledge or labelled datasets. Therefore, subsequent works propose unsupervised approaches based on generative models to learn these representations. Recently, representations learned with self-supervised contrastive loss-based methods have yielded state-of-the-art results on various imaging tasks compared to earlier unsupervised approaches. In this work, we leverage a contrastive learning framework to learn appropriate representations from single-cell fluorescent microscopy images for the task of Mechanism-of-Action classification. The proposed work is evaluated on the annotated BBBC021 dataset, and we obtain state-of-the-art results in NSC, NCSB and drop metrics for an unsupervised approach. We observe an improvement of 10% in NCSB accuracy and 11% in NSC-NSCB drop over the previously best unsupervised method. Moreover, the performance of our unsupervised approach ties with the best supervised approach. Additionally, we observe that our framework performs well even without post-processing, unlike earlier methods. With this, we conclude that one can learn robust cell representations with contrastive learning.
Leverage (statistics)
Feature Learning
Supervised Learning
Cite
Citations (0)
Contrastive representation learning has shown to be an effective way of learning representations from unlabeled data. However, much progress has been made in vision domains relying on data augmentations carefully designed using domain knowledge. In this work, we propose i-Mix, a simple yet effective regularization strategy for improving contrastive representation learning in both vision and non-vision domains. We cast contrastive learning as training a non-parametric classifier by assigning a unique virtual class to each data in a batch. Then, data instances are mixed in both the input and virtual label spaces, providing more augmented data during training. In experiments, we demonstrate that i-Mix consistently improves the quality of self-supervised representations across domains, resulting in significant performance gains on downstream tasks. Furthermore, we confirm its regularization effect via extensive ablation studies across model and dataset sizes. The code will be released.
Regularization
Feature Learning
Training set
Labeled data
Representation
Cite
Citations (16)
Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset i.e., the amount of data available with ground truth. Learning algorithms try to generalize solely based on the data that it is presented with during the training. In this work, we propose an inductive transfer learning method that can augment learning models by infusing similar instances from different learning tasks in Natural Language Processing (NLP) domain. We propose to use instance representations from a source dataset, without inheriting anything else from the source learning model. Representations of the instances of source and target datasets are learned, retrieval of relevant source instances is performed using soft-attention mechanism and locality sensitive hashing and then augmented into the model during training on the target dataset. Therefore, while learning from a training data, we also simultaneously exploit and infuse relevant local instance-level information from an external data. Using this approach we have shown significant improvements over the baseline for three major news classification datasets. Experimental evaluations also show that the proposed approach reduces dependency on labeled data by a significant margin for comparable performance. With our proposed cross dataset learning procedure we show that one can achieve competitive/better performance than learning from a single dataset.
Locality-sensitive hashing
Transfer of learning
Margin (machine learning)
Baseline (sea)
Ground truth
Cite
Citations (5)
In this work, we evaluate contrastive models for the task of image retrieval. We hypothesise that models that are learned to encode semantic similarity among instances via discriminative learning should perform well on the task of image retrieval, where relevancy is defined in terms of instances of the same object. Through our extensive evaluation, we find that representations from models trained using contrastive methods perform on-par with (and outperforms) a pre-trained supervised baseline trained on the ImageNet labels in retrieval tasks under various configurations. This is remarkable given that the contrastive models require no explicit supervision. Thus, we conclude that these models can be used to bootstrap base models to build more robust image retrieval engines.
Discriminative model
Similarity (geometry)
ENCODE
Contextual image classification
Cite
Citations (23)
Learning image representations without human supervision is an important and active research field. Several recent approaches have successfully leveraged the idea of making such a representation invariant under different types of perturbations, especially via contrastive-based instance discrimination training. Although effective visual representations should indeed exhibit such invariances, there are other important characteristics, such as encoding contextual reasoning skills, for which alternative reconstruction-based approaches might be better suited.With this in mind, we propose a teacher-student scheme to learn representations by training a convolutional net to reconstruct a bag-of-visual-words (BoW) representation of an image, given as input a perturbed version of that same image. Our strategy performs an online training of both the teacher network (whose role is to generate the BoW targets) and the student network (whose role is to learn representations), along with an online update of the visual-words vocabulary (used for the BoW targets). This idea effectively enables fully online BoW-guided unsupervised learning. Extensive experiments demonstrate the interest of our BoWbased strategy, which surpasses previous state-of-the-art methods (including contrastive-based ones) in several applications. For instance, in downstream tasks such Pascal object detection, Pascal classification and Places205 classification, our method improves over all prior unsupervised approaches, thus establishing new state-of-the-art results that are also significantly better even than those of supervised pre-training. We provide the implementation code at https://github.com/valeoai/obow.
Pascal (unit)
Feature Learning
Bag-of-words model
Cite
Citations (57)
Pre-training convolutional neural networks with weakly-supervised and self-supervised strategies is becoming increasingly popular for several computer vision tasks. However, due to the lack of strong discriminative signals, these learned representations may overfit to the pre-training objective (e.g., hashtag prediction) and not generalize well to downstream tasks. In this work, we present a simple strategy - ClusterFit to improve the robustness of the visual representations learned during pre-training. Given a dataset, we (a) cluster its features extracted from a pre-trained network using k-means and (b) re-train a new network from scratch on this dataset using cluster assignments as pseudo-labels. We empirically show that clustering helps reduce the pre-training task-specific information from the extracted features thereby minimizing overfitting to the same. Our approach is extensible to different pre-training frameworks -- weak- and self-supervised, modalities -- images and videos, and pre-training tasks -- object and action classification. Through extensive transfer learning experiments on 11 different target datasets of varied vocabularies and granularities, we show that ClusterFit significantly improves the representation quality compared to the state-of-the-art large-scale (millions / billions) weakly-supervised image and video models and self-supervised image models.
Overfitting
Discriminative model
Robustness
Transfer of learning
Supervised Learning
Task Analysis
Cite
Citations (95)
Existing self-supervised learning (SSL) methods are mostly applied for training representation models from artificially balanced datasets (e.g., ImageNet). It is unclear how well they will perform in the practical scenarios where datasets are often imbalanced w.r.t. the classes. Motivated by this question, we conduct a series of studies on the performance of self-supervised contrastive learning and supervised learning methods over multiple datasets where training instance distributions vary from a balanced one to a long-tailed one. Our findings are quite intriguing. Different from supervised methods with large performance drop, the self-supervised contrastive learning methods perform stably well even when the datasets are heavily imbalanced. This motivates us to explore the balanced feature spaces learned by contrastive learning, where the feature representations present similar linear separability w.r.t. all the classes. Our further experiments reveal that a representation model generating a balanced feature space can generalize better than that yielding an imbalanced one across multiple settings. Inspired by these insights, we develop a novel representation learning method, called k-positive contrastive learning. It effectively combines strengths of the supervised method and the contrastive learning method to learn representations that are both discriminative and balanced. Extensive experiments demonstrate its superiority on multiple recognition tasks. Remarkably, it achieves new state-of-the-art on challenging long-tailed recognition benchmarks. Code and models will be released.
Feature Learning
Discriminative model
Feature (linguistics)
Representation
Feature vector
Supervised Learning
Cite
Citations (56)