Related papers: Decoupled Classification Refinement: Hard False Po…

Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Standard fine-tuning of pre-trained audio models couples representation learning with classifier training, which can obscure the true quality of the learned representations. In this work, we advocate for a disentangled two-stage framework…

Implicit degradation modeling-based blind super-resolution (SR) has attracted more increasing attention in the community due to its excellent generalization to complex degradation scenarios and wide application range. How to extract more…

Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm. Existing deep ensemble methods usually naively train many different models and then aggregate their predictions. This is…

Trained using only image class label, deep weakly supervised methods allow image classification and ROI segmentation for interpretability. Despite their success on natural images, they face several challenges over histology data where ROI…

Multi-label class-incremental learning (MLCIL) continuously expands the label space while recognizing multiple co-occurring classes, making it prone to catastrophic forgetting and high false-positive rates (FPR). Extending CLIP to MLCIL is…

This paper proposes a novel loss function for training a distributed convolutional neural network (DisCNN) to recognize only a specific positive class. By mapping positive samples to a compact set in high-dimensional space and negative…

Current medical image classification efforts mainly aim for higher average performance, often neglecting the balance between different classes. This can lead to significant differences in recognition accuracy between classes and obvious…

Multi-view 3D object detection systems often struggle with generating precise predictions due to the challenges in estimating depth from images, increasing redundant and incorrect detections. Our paper presents Ray Denoising, an innovative…

The limited understanding capacity of the visual encoder in Contrastive Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance. This capacity includes both Discriminative Ability (D-Ability), which…

Camouflaged object detection (COD) primarily relies on semantic or instance segmentation methods. While these methods have made significant advancements in identifying the contours of camouflaged objects, they may be inefficient or…

Collaborative filtering (CF), as a standard method for recommendation with implicit feedback, tackles a semi-supervised learning problem where most interaction data are unobserved. Such a nature makes existing approaches highly rely on…

Reducing false positives is essential for enhancing object detector performance, as reflected in the mean Average Precision (mAP) metric. Although object detectors have achieved notable improvements and high mAP scores on the COCO dataset,…

We address the problem of weakly supervised object localization where only image-level annotations are available for training object detectors. Numerous methods have been proposed to tackle this problem through mining object proposals.…

Channel pruning is one of the important methods for deep model compression. Most of existing pruning methods mainly focus on classification. Few of them conduct systematic research on object detection. However, object detection is different…

Object detection involves two sub-tasks, i.e. localizing objects in an image and classifying them into various categories. For existing CNN-based detectors, we notice the widespread divergence between localization and classification, which…

Contrastive learning has achieved promising performance in the field of multi-view clustering recently. However, the positive and negative sample construction mechanisms ignoring semantic consistency lead to false negative pairs, limiting…

Although deep learning has shown great success in recent years, researchers have discovered a critical flaw where small, imperceptible changes in the input to the system can drastically change the output classification. These attacks are…

In dense retrieval, effective training hinges on selecting high quality hard negatives while avoiding false negatives. Recent methods apply heuristics based on positive document scores to identify hard negatives, improving both performance…

We propose Rank & Sort (RS) Loss, a ranking-based loss function to train deep object detection and instance segmentation methods (i.e. visual detectors). RS Loss supervises the classifier, a sub-network of these methods, to rank each…