The design for mixed-precision networks that achieves optimized tradeoffs corresponds to an architecture that supports 1, 2, and 4-bit fixed-point operations with four configurable precision patterns, when coupled with system-aware training and inference optimization -- networks trained for this design achieve accuracies that closely match full-precision accuracies, while compressing and improving run-time efficiency of the neural networks drastically by 10-20x, compared to full-precision networks.
Our results demonstrate that the dataflow that keeps outputs in SIMD registers while also maximizing both input and weight reuse consistently yields the best performance for a wide variety of inference workloads, achieving up to 3x speedup for 8-bit neural networks, and up to 4. 8x speedup for binary neural networks, respectively, over the optimized implementations of neural networks today.
In this paper, we focus on developing knowledge distillation (KD) for compact 3D detectors.
One natural approach is to use 1-bit CNNs to reduce the computation and memory cost of NAS by taking advantage of the strengths of each in a unified framework, while searching the 1-bit CNNs is more challenging due to the more complicated processes involved.
Vision transformers (ViTs) quantization offers a promising prospect to facilitate deploying large pre-trained networks on resource-limited devices.
At the upper level, we introduce a new foreground-aware query matching scheme to effectively transfer the teacher information to distillation-desired features to minimize the conditional information entropy.
IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework, where the implicit neural representation is adopted in the decoding process to learn continuous-resolution representation.
Ranked #1 on Image Super-Resolution on CelebA-HQ 128x128
C-BBL quantizes continuous labels into grids and formulates two-hot ground truth labels.
1 code implementation • 9 Feb 2023 • Shengchao Liu, Yanjing Li, Zhuoxinran Li, Anthony Gitter, Yutao Zhu, Jiarui Lu, Zhao Xu, Weili Nie, Arvind Ramanathan, Chaowei Xiao, Jian Tang, Hongyu Guo, Anima Anandkumar
Current AI-assisted protein design mainly utilizes protein sequential and structural information.
In this paper, we introduce a Resilient Binary Neural Network (ReBNN) to mitigate the frequent oscillation for better BNNs' training.
The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices.
This explains why existing KD methods are less effective for 1-bit detectors, caused by a significant information discrepancy between the real-valued teacher and the 1-bit student.
To address this issue, Recurrent Bilinear Optimization is proposed to improve the learning process of BNNs (RBONNs) by associating the intrinsic bilinear variables in the back propagation process.
Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices.
Real-time point cloud processing is fundamental for lots of computer vision tasks, while still challenged by the computational problem on resource-limited edge devices.
In this work, we present an end-to-end framework to settle data association in online Multiple-Object Tracking (MOT).