Generative Prompt Model for Weakly Supervised Object Localization
0
Citation
0
Reference
10
Related Paper
Abstract:
Weakly supervised object localization (WSOL) remains challenging when learning object localization models from image category labels. Conventional methods that discriminatively train activation models ignore representative yet less discriminative object parts. In this study, we propose a generative prompt model (GenPromp), defining the first generative pipeline to localize less discriminative object parts by formulating WSOL as a conditional image denoising procedure. During training, GenPromp converts image category labels to learnable prompt embeddings which are fed to a generative model to conditionally recover the input image with noise and learn representative embeddings. During inference, enPromp combines the representative embeddings with discriminative embeddings (queried from an off-the-shelf vision-language model) for both representative and discriminative capacity. The combined embeddings are finally used to generate multi-scale high-quality attention maps, which facilitate localizing full object extent. Experiments on CUB-200-2011 and ILSVRC show that GenPromp respectively outperforms the best discriminative models by 5.2% and 5.6% (Top-1 Loc), setting a solid baseline for WSOL with the generative model. Code is available at https://github.com/callsys/GenPromp.Keywords:
Discriminative model
Generative model
Code (set theory)
Machine learning-based unfolding has enabled unbinned and high-dimensional differential cross section measurements. Two main approaches have emerged in this research area: one based on discriminative models and one based on generative models. The main advantage of discriminative models is that they learn a small correction to a starting simulation while generative models scale better to regions of phase space with little data. We propose to use Schroedinger Bridges and diffusion models to create SBUnfold, an unfolding approach that combines the strengths of both discriminative and generative models. The key feature of SBUnfold is that its generative model maps one set of events into another without having to go through a known probability density as is the case for normalizing flows and standard diffusion models. We show that SBUnfold achieves excellent performance compared to state of the art methods on a synthetic Z+jets dataset.
Discriminative model
Generative model
Feature (linguistics)
Cite
Citations (2)
We present a general framework for dependency parsing of Italian sentences based on a combination of discriminative and generative models. We use a state-of-the-art discriminative model to obtain a k-best list of candidate structures for the test sentences, and use the generative model to compute the probability of each candidate, and select the most probable one. We present the details of the specific generative model we have employed for the EVALITA'09 task. Results show that by using the generative model we gain around 1% in labeled accuracy (around 7% error reduction) over the discriminative model.
Discriminative model
Generative model
Dependency grammar
Cite
Citations (0)
- List of Figures. List of Tables. - Preface. Acknowledgments. - 1. Introduction. - 2. Generative Versus Discriminative Learning. - 3. Maximum Entropy Discrimination. - 4. Extensions To MED. - 5. Latent Discrimination. - 6. Conclusion. - 7. Appendix. - Index.
Discriminative model
Generative model
Cite
Citations (165)
This paper presents an adaptive discriminative generative model that generalizes the conventional Fisher Linear Discriminant algorithm and renders a proper probabilistic interpretation. Within the context of object tracking, we aim to find a discriminative generative model that best separates the target from the background. We present a computationally efficient algorithm to constantly update this discriminative model as time progresses. While most tracking algorithms operate on the premise that the object appearance or ambient lighting condition does not significantly change as time progresses, our method adapts a discriminative generative model to reflect appearance variation of the target and background, thereby facilitating the tracking task in ever-changing environments. Numerous experiments show that our method is able to learn a discriminative generative model for tracking target objects undergoing large pose and lighting changes.
Discriminative model
Generative model
Active appearance model
Generative Design
Cite
Citations (81)
Discriminative model
Generative model
Cite
Citations (0)
Uncovering data generative factors is the ultimate goal of disentanglement learning. Although many works proposed disentangling generative models able to uncover the underlying generative factors of a dataset, so far no one was able to uncover OOD generative factors (i.e., factors of variations that are not explicitly shown on the dataset). Moreover, the datasets used to validate these models are synthetically generated using a balanced mixture of some predefined generative factors, implicitly assuming that generative factors are uniformly distributed across the datasets. However, real datasets do not present this property. In this work we analyse the effect of using datasets with unbalanced generative factors, providing qualitative and quantitative results for widely used generative models. Moreover, we propose TC-VAE, a generative model optimized using a lower bound of the joint total correlation between the learned latent representations and the input data. We show that the proposed model is able to uncover OOD generative factors on different datasets and outperforms on average the related baselines in terms of downstream disentanglement metrics.
Generative model
Generative Design
Cite
Citations (0)
Discriminative model
Generative model
Identification
Cite
Citations (0)
Weakly supervised object localization (WSOL) remains challenging when learning object localization models from image category labels. Conventional methods that discriminatively train activation models ignore representative yet less discriminative object parts. In this study, we propose a generative prompt model (GenPromp), defining the first generative pipeline to localize less discriminative object parts by formulating WSOL as a conditional image denoising procedure. During training, GenPromp converts image category labels to learnable prompt embeddings which are fed to a generative model to conditionally recover the input image with noise and learn representative embeddings. During inference, enPromp combines the representative embeddings with discriminative embeddings (queried from an off-the-shelf vision-language model) for both representative and discriminative capacity. The combined embeddings are finally used to generate multi-scale high-quality attention maps, which facilitate localizing full object extent. Experiments on CUB-200-2011 and ILSVRC show that GenPromp respectively outperforms the best discriminative models by 5.2% and 5.6% (Top-1 Loc), setting a solid baseline for WSOL with the generative model. Code is available at https://github.com/callsys/GenPromp.
Discriminative model
Generative model
Code (set theory)
Cite
Citations (0)
The ability to accurately model the content structure of text is important for many natural language processing applications. This paper describes experiments with generative models for analyzing the discourse structure of medical abstracts, which generally follow the pattern of "introduction", "methods", "results", and "conclusions". We demonstrate that Hidden Markov Models are capable of accurately capturing the structure of such texts, and can achieve classification accuracy comparable to that of discriminative techniques. In addition, generative approaches provide advantages that may make them preferable to discriminative techniques such as Support Vector Machines under certain conditions. Our work makes two contributions: at the application level, we report good performance on an interesting task in an important domain; more generally, our results contribute to an ongoing discussion regarding the tradeoffs between generative and discriminative techniques.
Discriminative model
Generative model
Cite
Citations (29)
Weakly supervised object localization (WSOL) remains challenging when learning object localization models from image category labels. Conventional methods that discriminatively train activation models ignore representative yet less discriminative object parts. In this study, we propose a generative prompt model (GenPromp), defining the first generative pipeline to localize less discriminative object parts by formulating WSOL as a conditional image denoising procedure. During training, GenPromp converts image category labels to learnable prompt embeddings which are fed to a generative model to conditionally recover the input image with noise and learn representative embeddings. During inference, GenPromp combines the representative embeddings with discriminative embeddings (queried from an off-the-shelf vision-language model) for both representative and discriminative capacity. The combined embeddings are finally used to generate multi-scale high-quality attention maps, which facilitate localizing full object extent. Experiments on CUB-200-2011 and ILSVRC show that GenPromp respectively outperforms the best discriminative models by 5.2% and 5.6% (Top-1 Loc), setting a solid baseline for WSOL with the generative model. Code is available at https://github.com/callsys/GenPromp.
Discriminative model
Generative model
Code (set theory)
Cite
Citations (11)