However, except for the backbone networks, other detector components, such as the detector head and the feature pyramid network, remain randomly initialized, which hinders the consistency between detectors and pre-trained models.
Ranked #1 on Few-Shot Object Detection on MS-COCO (10-shot)
The existing pipeline is first pretraining a source model (which contains a generator and a discriminator) on a large-scale dataset and finetuning it on a target domain with limited samples.
Weakly supervised object localization (WSOL) aims at learning to localize objects of interest by only using the image-level labels as the supervision.
Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection.
Ranked #1 on Active Object Detection on PASCAL VOC 07+12
TS-CAM finally couples the patch tokens with the semantic-agnostic attention map to achieve semantic-aware localization.
This paper presents a novel design of a soft tactile finger with omni-directional adaptation using multi-channel optical fibers for rigid-soft interactive grasping.
We present Domain Contrast (DC), a simple yet effective approach inspired by contrastive learning for training domain adaptive detectors.
We present benchmarking results of the DeepClaw system for a baseline Tic-Tac-Toe task, a bin-clearing task, and a jigsaw puzzle task using three sets of standard robotic hardware.
Weakly-supervised action localization requires training a model to localize the action segments in the video given only video level action label.
Ranked #8 on Weakly Supervised Action Localization on THUMOS’14
This paper presents preliminary results of the design, development, and evaluation of a hand rehabilitation glove fabricated using lobster-inspired hybrid design with rigid and soft components for actuation.
Many researchers have identified robotics as a potential solution to the aging population faced by many developed and developing countries.
Such reconfigurable design with these omni-adaptive fingers enables us to systematically investigate the optimal arrangement of the fingers towards robust grasping.
Robotic fingers made of soft material and compliant structures usually lead to superior adaptation when interacting with the unstructured physical environment.
We use soft, stuffed toys for training, instead of everyday objects, to reduce the integration complexity and computational burden and exploit such rigid-soft interaction by changing the gripper fingers to the soft ones when dealing with rigid, daily-life items such as the Yale-CMU-Berkeley (YCB) objects.
In this study, we propose a learning-to-match approach to break IoU restriction, allowing objects to match anchors in a flexible manner.
Ranked #107 on Object Detection on COCO test-dev
Weakly supervised object detection (WSOD) focuses on training object detector with only image-level annotations, and is challenging due to the gap between the supervision and the objective.
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors.
Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors.
Ranked #14 on Weakly Supervised Object Detection on PASCAL VOC 2007
In particular, the advantage of CHR is more significant in the scenarios with fewer positive training samples, which demonstrates its potential application in real-world security inspection.
In this paper, we describe the design of a hybrid neural network for logical learning that is similar to the human reasoning through the introduction of an auxiliary input, namely the indicators, that act as the hints to suggest logical outcomes.