Related papers: IF-Net: An Illumination-invariant Feature Network

Integrating a foreground object into a background scene with illumination harmonization is an important but challenging task in computer vision and augmented reality community. Existing methods mainly focus on foreground and background…

Object Detection is the task of identifying the existence of an object class instance and locating it within an image. Difficulties in handling high intra-class variations constitute major obstacles to achieving high performance on standard…

Clothing-change person re-identification (CC Re-ID) has attracted increasing attention in recent years due to its application prospect. Most existing works struggle to adequately extract the ID-related information from the original RGB…

In contrast to comparing faces via single exemplars, matching sets of face images increases robustness and discrimination performance. Recent image set matching approaches typically measure similarities between subspaces or manifolds, while…

In general, intrinsic image decomposition algorithms interpret shading as one unified component including all photometric effects. As shading transitions are generally smoother than reflectance (albedo) changes, these methods may fail in…

We live in a dynamic world where things change all the time. Given two images of the same scene, being able to automatically detect the changes in them has practical applications in a variety of domains. In this paper, we tackle the change…

As 3D perception problems grow in popularity and the need for large-scale labeled datasets for LiDAR semantic segmentation increase, new methods arise that aim to reduce the necessity for dense annotations by employing weakly-supervised…

This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting. Many approaches achieve alpha mattes with complex encoders to extract robust semantics, then resort to the…

In recent years, convolutional neural networks (CNNs) have achieved impressive performance for various visual recognition scenarios. CNNs trained on large labeled datasets can not only obtain significant performance on most challenging…

Knowledge distillation has shown great success in classification, however, it is still challenging for detection. In a typical image for detection, representations from different locations may have different contributions to detection…

Learning good feature embeddings for images often requires substantial training data. As a consequence, in settings where training data is limited (e.g., few-shot and zero-shot learning), we are typically forced to use a generic feature…

The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly.…

Knowledge distillation is a widely used paradigm for inheriting information from a complicated teacher network to a compact student network and maintaining the strong performance. Different from image classification, object detectors are…

The robustness of image recognition algorithms remains a critical challenge, as current models often depend on large quantities of labeled data. In this paper, we propose a hybrid approach that combines the adaptability of neural networks…

We introduce a learning-based approach to detect repeatable keypoints under drastic imaging changes of weather and lighting conditions to which state-of-the-art keypoint detectors are surprisingly sensitive. We first identify good keypoint…

Place recognition is a challenging problem in mobile robotics, especially in unstructured environments or under viewpoint and illumination changes. Most LiDAR-based methods rely on geometrical features to overcome such challenges, as…

Image identification is one of the most challenging tasks in different areas of computer vision. Scale-invariant feature transform is an algorithm to detect and describe local features in images to further use them as an image matching…

Hypernetworks are models that generate or modulate the weights of another network. They provide a flexible mechanism for injecting context and task conditioning and have proven broadly useful across diverse applications without significant…

Few-shot Intent Detection is challenging due to the scarcity of available annotated utterances. Although recent works demonstrate that multi-level matching plays an important role in transferring learned knowledge from seen training classes…

Finding point-wise correspondences between images is a long-standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport…