Spotlight the Negatives: A Generalized Discriminative Latent Model
Discriminative latent variable models (LVM) are frequently applied to various visual recognition tasks. In these systems the latent (hidden) variables provide a formalism for modeling structured variation of visual features. Conventionally, latent variables are de- fined on the variation of the foreground (positive) class. In this work we augment LVMs to include negative latent variables corresponding to the background class. We formalize the scoring function of such a generalized LVM (GLVM). Then we discuss a framework for learning a model based on the GLVM scoring function. We theoretically showcase how some of the current visual recognition methods can benefit from this generalization. Finally, we experiment on a generalized form of Deformable Part Models with negative latent variables and show significant improvements on two different detection tasks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning
Most studies in zero-shot learning model the relationship, in the form of a classifier or mapping, between features from images of seen classes and their attributes. Therefore, the degree of a model's generalization abil…
DisentanglementGeneralized Zero-Shot LearningZero-Shot LearningWhen Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriever score rather than diagnostic value, a…
Contrastive LearningCLIP-Lung: Textual Knowledge-Guided Lung Nodule Malignancy Prediction
Lung nodule malignancy prediction has been enhanced by advanced deep-learning techniques and effective tricks. Nevertheless, current methods are mainly trained with cross-entropy loss using one-hot categorical labels, wh…
AttributeContrastive LearningPoselet Key-Framing: A Model for Human Activity Recognition
In this paper, we develop a new model for recognizing human actions. An action is modeled as a very sparse sequence of temporally local discriminative keyframes collections of partial key-poses of the actor(s), depicting…
Activity RecognitionHuman Activity RecognitionTemporal LocalizationUnsupervised Training of Vision Transformers with Synthetic Negatives
This paper does not introduce a novel method per se. Instead, we address the neglected potential of hard negative samples in self-supervised learning. Previous works explored synthetic hard negatives but rarely in the co…
Self-Supervised LearningRepresentation Learning