8 accepted papers
Contrastive representation learning has been validated its effectiveness to knowledge distillation. However, its dynamically updated representations largely impede the improvement of student performance. We propose to append a compact but effective project layer to both teacher and student models. W…
Feature-map based knowledge distillation has exhibited its significance in improving the performance of student model. Existing works mainly focus on the formulation of knowledge, but ignore the number difference of channels due to heterogeneous architectures of teacher-student pair. They generally…
Intermediate feature maps of teacher model can produce enriched knowledge to improve the performance of student model. Existing works mainly focus on formulating beneficial knowledge for transferring, but ignore the contribution discrepancy of the knowledge to promote performance. To tackle this iss…
Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current models, leading to image distortion and temporal inconsistency. We point out the necessity of exploring multi-freque…
The extensive computational burden limits the usage of accurate but complex object detectors in resource-bounded scenarios. In this paper, we present a lightweight object detector, named LightDet, to address this dilemma. We design a lightweight backbone that is able to capture rich low-level featur…
Semantic scene completion predicts volumetric occupancy and object category of a 3D scene, which helps intelligent agents to understand and interact with the surroundings. In this work, we propose a disentangled framework, sequentially carrying out 2D semantic segmentation, 2D-3D reprojection and 3D…
Unsupervised video prediction is a very challenging task due to the complexity and diversity in natural scenes. Prior works directly predicting pixels or optical flows either have the blurring problem or require additional assumptions. We highlight that the crux for video frame prediction lies in pr…
Depth estimation from a single image is very challenging due to the inherent ambiguity of mapping a color image to a depth map. Previous work tackles this problem by exploiting various levels of features with multi-scale deep convolutional neural networks. However, most of the local geometric struct…