An investigation of auditory dimensional interaction in a bivariate bilateral conditioning paradigm in the rabbit
0
Citation
44
Reference
10
Related Paper
Abstract:
The current study adapted the Garner paradigm for diagnosing separable versus integral perceptual dimensions to the eye-blink classical conditioning paradigm using rabbits. Specifically, this study examined the ability of rabbits to categorize stimuli based on one auditory dimension while ignoring a second, irrelevant dimension by displaying an appropriate eye-blink for bilaterally conditioned discriminative responses. Tones used in training varied along two dimensions, starting frequency and magnitude of frequency sweep upwards from the start. Rabbits first learned to categorize along a single dimension (blinking one eye for one category response and the other eye for the other response) and then continued to categorize tones in a second phase in which the irrelevant dimension was varied. The variation of the irrelevant dimension did not disrupt performance, indicating that rabbits perceive these dimensions as separable.Keywords:
Discriminative model
Discriminative model
Cite
Citations (2)
Currently, most top-performing Weakly supervised Fine-grained Image Classification (WFGIC) schemes tend to pick out discriminative patches. However, those patches usually contain much noise information, which influences the accuracy of the classification. Besides, they rely on a large amount of candidate patches to discover the discriminative ones, thus leading to high computational cost. To address these problems, we propose a novel end-to-end Self-regressive Localization with Discriminative Prior Network (SDN) model, which learns to explore more accurate size of discriminative patches and enables to classify images in real time. Specifically, we design a multi-task discriminative learning network, a self-regressive localization sub-network and a discriminative prior sub-network with the guided loss as well as the consistent loss to simultaneously learn self-regressive coefficients and discriminative prior maps. The self-regressive coefficients can decrease noise information in discriminative patches and the discriminative prior maps through learning discriminative probability values filter thousands of candidate patches to single figure. Extensive experiments demonstrate that the proposed SDN model achieves state-of-the-art both in accuracy and efficiency.
Discriminative model
Contextual image classification
Cite
Citations (3)
We can categorize our environment into different scene categories (e.g., a kitchen or a highway) within a glance. Object information has been suggested to play a crucial role in this process, and some proposals even claim that recognition of a single object can be sufficient to categorize the scene around it. Here, we tested this claim by having participants categorize real-world scene photographs reduced to a single, cut-out object. We show that single objects can indeed be sufficient for correct scene categorization and that scene category information can be extracted within 50 ms of object presentation. Furthermore, we identify the exact properties that make certain objects diagnostic of scene categories using human ratings and statistical measures derived from labelled image databases. Interestingly, fast scene categorization is best explained by human ratings of estimated frequency and specificity of the presented objects for the target scene category and less so by objective database measures. Taken together, our findings support a central role of object information during fast scene categorization, showing that single objects can be indicative of a scene category if they are assumed to frequently and exclusively occur in a certain environment.
Scene statistics
Presentation (obstetrics)
Cite
Citations (0)
Categorization is the act of responding differently to objects or events in separate classes or categories. It is a vitally important skill that allows us to approach friends and escape foes, to find food, and avoid toxins. The scientific study of categorization has a long history. For most of this time, the focus was on the cognitive processes that mediate categorization. Within the past decade, however, considerable attention has shifted to the study of the neural basis of categorization. This chapter reviews that work. It begins with a brief overview of the basal ganglia, which are a collection of subcortical nuclei that are especially important in categorization. It then focuses on initial category learning and considers the neural basis of automatic categorization judgements.
Cite
Citations (4)
The advancements in generative modeling, particularly the advent of diffusion models, have sparked a fundamental question: how can these models be effectively used for discriminative tasks? In this work, we find that generative models can be great test-time adapters for discriminative models. Our method, Diffusion-TTA, adapts pre-trained discriminative models such as image classifiers, segmenters and depth predictors, to each unlabelled example in the test set using generative feedback from a diffusion model. We achieve this by modulating the conditioning of the diffusion model using the output of the discriminative model. We then maximize the image likelihood objective by backpropagating the gradients to discriminative model's parameters. We show Diffusion-TTA significantly enhances the accuracy of various large-scale pre-trained discriminative models, such as, ImageNet classifiers, CLIP models, image pixel labellers and image depth predictors. Diffusion-TTA outperforms existing test-time adaptation methods, including TTT-MAE and TENT, and particularly shines in online adaptation setups, where the discriminative model is continually adapted to each example in the test set. We provide access to code, results, and visualizations on our website: https://diffusion-tta.github.io/.
Discriminative model
Generative model
Cite
Citations (0)
Categorization is an interactive process between human’s cognitive activity and nature. The result of categorization forms category. During categorization, the co-action of many factors results in cognitive differences for the same category prototype. Using the theories related to category and categorization to analyze the cognitive differences can find out the reasons for the differences, which mainly contain culture, living environment, scientific development, living experience and age.
Cite
Citations (0)
Discriminative localization is essential for fine-grained image classification task, which devotes to recognizing hundreds of subcategories in the same basic-level category. Reflecting on discriminative regions of objects, key differences among different subcategories are subtle and local. Existing methods generally adopt a two-stage learning framework: The first stage is to localize the discriminative regions of objects, and the second is to encode the discriminative features for training classifiers. However, these methods generally have two limitations: (1) Separation of the two-stage learning is time-consuming. (2) Dependence on object and parts annotations for discriminative localization learning leads to heavily labor-consuming labeling. It is highly challenging to address these two important limitations simultaneously. Existing methods only focus on one of them. Therefore, this paper proposes the discriminative localization approach via saliency-guided Faster R-CNN to address the above two limitations at the same time, and our main novelties and advantages are: (1) End-to-end network based on Faster R-CNN is designed to simultaneously localize discriminative regions and encode discriminative features, which accelerates classification speed. (2) Saliency-guided localization learning is proposed to localize the discriminative region automatically, avoiding labor-consuming labeling. Both are jointly employed to simultaneously accelerate classification speed and eliminate dependence on object and parts annotations. Comparing with the state-of-the-art methods on the widely-used CUB-200-2011 dataset, our approach achieves both the best classification accuracy and efficiency.
Discriminative model
ENCODE
Cite
Citations (52)
Discriminative learning of sparse-code based dictionaries tends to be inherently unstable. We show that using a discriminative version of the deviation function to learn such dictionaries leads to a more stable formulation that can handle the reconstruction/discrimination trade-off in a principled manner. Results on Graz02 and UCF Sports datasets validate the proposed formulation.
Discriminative model
Dictionary Learning
Code (set theory)
Cite
Citations (6)
The article looks at idioms as categorization means. On the basis of linguistic analysis of semantic organization of idioms two patterns of idiomatic categorization are argued — general categorization and relevant property based categorization. Cognitive functions of idioms differ with regard to their role as categorization means, idioms can serve different categorization purposes according to two general cognitive processes — static and dynamic — including in a category or considering the given qualities as the reasons for categorization. Moreover, the purpose of categorization was investigated with defining the specificity of the phenomena and its types. The categorization purpose was conceived as different types of information e.g. behavioral expectations or interaction models with the object. The cause-effect relationship between the category and the categorization purpose was claimed.
Cite
Citations (1)
Categorization researchers typically present single objects to be categorized. But real-world categorization often involves object recognition within complex scenes. It is unknown how the processes of categorization stand up to visual complexity or why they fail facing it. The authors filled this research gap by blending the categorization and visual-search paradigms into a visual-search and categorization task in which participants searched for members of target categories in complex displays. Participants have enormous difficulty in this task. Despite intensive and ongoing category training, they detect targets at near-chance levels unless displays are extremely simple or target categories extremely focused. These results, discussed from the perspectives of categorization and visual search, might illuminate societally important instances of visual search (e.g., diagnostic medical screening).
Visual Search
Cite
Citations (36)