Related papers: Aligning Pretraining for Detection via Object-Leve…

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment.…

Self-supervised learning has been successfully applied to pre-train video representations, which aims at efficient adaptation from pre-training domain to downstream tasks. Existing approaches merely leverage contrastive loss to learn…

Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination. Scene-level methods tend to lose local details that are crucial for recognizing the road…

In recent years, driven by the need for safer and more autonomous transport systems, the automotive industry has shifted toward integrating a growing number of Advanced Driver Assistance Systems (ADAS). Among the array of sensors employed…

Pre-training is a dominant paradigm in computer vision. For example, supervised ImageNet pre-training is commonly used to initialize the backbones of object detection and segmentation models. He et al., however, show a surprising result…

Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often…

Image fusion is a crucial technique in the field of computer vision, and its goal is to generate high-quality fused images and improve the performance of downstream tasks. However, existing fusion methods struggle to balance these two…

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…

Weakly Supervised Object Detection (WSOD) is a task that detects objects in an image using a model trained only on image-level annotations. Current state-of-the-art models benefit from self-supervised instance-level supervision, but since…

We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on instance-discriminative contrastive learning are not as…

Recently, pretext-task based methods are proposed one after another in self-supervised video feature learning. Meanwhile, contrastive learning methods also yield good performance. Usually, new methods can beat previous ones as claimed that…

Given a collection of images, humans are able to discover landmarks by modeling the shared geometric structure across instances. This idea of geometric equivariance has been widely used for the unsupervised discovery of object landmark…

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative…

Contrastive learning is a form of self-supervision that can leverage unlabeled data to produce pretrained models. While contrastive learning has demonstrated promising results on natural image classification tasks, its application to…

This study proposes a semi-supervised co-training framework for object detection in densely packed retail environments, where limited labeled data and complex conditions pose major challenges. The framework combines Faster R-CNN (utilizing…

Pursuing realistic results according to human visual perception is the central concern in the image transformation tasks. Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on…

The next token prediction loss is the dominant self-supervised training objective for large language models and has achieved promising results in a variety of downstream tasks. However, upon closer investigation of this objective, we find…

Recent masked image modeling (MIM) has received much attention in self-supervised learning (SSL), which requires the target model to recover the masked part of the input image. Although MIM-based pre-training methods achieve new…

Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task. Most existing works are dedicated to establishing specialized modules to identify…

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank.…