Convolutional neural networks (CNNs) have achieved great successes in face recognition, which unfortunately comes at the cost of massive computation and storage consumption. Many compact face recognition networks are thus proposed to resolve this problem, and triplet loss is effective to further improve the performance of these compact models. However, it normally employs a fixed margin to all the samples, which neglects the informative similarity structures between different identities. In this paper, we borrow the idea of knowledge distillation and define the informative similarity as the transferred knowledge. Then, we propose an enhanced version of triplet loss, named triplet distillation, which exploits the capability of a teacher model to transfer the similarity information to a student model by adaptively varying the margin between positive and negative pairs. Experiments on the LFW, AgeDB and CPLFW datasets show the merits of our method compared to the original triplet loss.

A vector quantization (VQ) scheme with finite memory called dynamic finite-state vector quantization (DFSVQ) is presented. The encoder consists of a large codebook, so called super-codebook, where for each input vector a fixed number of its codevectors are chosen to generate a much smaller codebook (sub-codebook). This sub-codebook represents the best matching codevectors that could be found in the super-codebook for encoding the current input vector. The choice for the codevectors in the sub-codebook is based on the information obtained from the previously encoded blocks where directional conditional block probability (histogram) matrices are used in the selection of the codevectors. The index of the best matching codevector in the sub-codebook is transmitted to the receiver. An adaptive DFSVQ scheme is also proposed in which, when encoding an input vector, first the sub-codebook is searched for a matching codevector to satisfy a pre-specified waveform distortion. If such a codevector is not found in tile current sub-codebook then the whole super-codebook is checked for a better match. If a better match is found then a signaling flag along with the corresponding index of the codevector is transmitted to the receiver. Both the DFSVQ encoder and its adaptive version are implemented. Experimental results for several monochrome images with a super-codebook size of 256 or 512 and different sub-codebook sizes are presented.>

A new VQ technique, adaptive multi-layer address-VQ, is introduced which exploits the interlock correlation by using several different address-codebooks organized in a hierarchical (multi-layer) manner. It is an error-free post-coding technique, which can apply to image, speech coding, and text compression. The quality (SNR value) of the images encoded by the proposed method is the same as that of a memoryless vector quantizer, but the bit rate is reduced by a factor of approximately 2.5-4.>

A vector quantization (VQ) scheme with memory called dynamic finite-state vector quantization (DFSVQ) is described. In the proposed DFSVQ system, a super-codebook is designed using the generalized Lloyd algorithm. During encoding, an input vector subcodebook is dynamically generated by reordering the positions of the codevectors in the super-codebook. The codevectors that are the most probable approximations of the input vector are therefore moved to the top of the super-codebook. The first N codevectors of the super-codebook form the subcodebook for that input vector. An adaptive DFSVQ scheme is proposed in which the subcodebook is searched for a matching codevector satisfying a prespecified waveform distortion when encoding an input vector. If such a codevector is not found in the current subcodebook, the whole super-codebook is checked for the best match and a signaling flag along with the corresponding address of the best-matching codevector is transmitted to the receiver.>

In this paper, a new approach of a variable block size VQ coding scheme is proposed. Most natural image can be divided into regions of high and low detail. Traditional coding schemes do not adapt the blocksize on the space-varying characteristics of natural images, but break the image into blocks of a fixed size prior to processing. The blocksize in transform coding is usually too large to handle partial high-detail region satisfactorily. On the other hand, the block size in conventional vector quantizer is too small to take advantage of large homogeneous regions in an image. For this reason, it can be very attractive to implement a variable block size image coding scheme which allow a greater variation of the number of bits spent per unit area according to the local detail.

A novel vector quantization scheme, called the address-vector quantizer (A-VQ), is proposed. It is based on exploiting the interblock correlation by encoding a group of blocks together using an address-codebook. The address-codebook consists of a set of address-codevectors where each codevector represents a combination of addresses (indexes). Each element of this codevector is an address of an entry in the LBG-codebook, representing a vector quantized block. The address-codebook consists of two regions: one is the active (addressable) region, and the other is the inactive (nonaddressable) region. During the encoding process the codevectors in the address-codebook are reordered adaptively in order to bring the most probable address-codevectors into the active region. When encoding an address-codevector, the active region of the address-codebook is checked, and if such an address combination exist its index is transmitted to the receiver. Otherwise, the address of each block is transmitted individually. The quality (SNR value) of the images encoded by the proposed A-VQ method is the same as that of a memoryless vector quantizer, but the bit rate would be reduced by a factor of approximately two when compared to a memoryless vector quantizer.>

The authors describe a novel adaptive vector quantization (VQ) scheme suitable for packet video. The technique is shown to provide flexibility in selecting the desired image quality, without the need to send the code vectors themselves. A large codebook is divided into two parts, called higher and lower priority sections, representing common and specific characteristics of images. Entries in the two sections are reorganized and/or exchanged as a function of the usage of the code vectors therein. The rate and extent of adaptation are dictated by the update interval and the desired level of quality, respectively, without requiring any transmission of the vectors themselves. Experimental results are presented.>

The authors extend the A-VQ (address-vector quantization) coding technique to encode RGB (red, green, blue) color images by utilizing the interblock and intercolor correlation. A modified A-VQ technique called dynamic address-vector quantization (DA-VQ) is introduced for encoding of color images. A multilayered address vector quantizer is also introduced, where the code vectors at each layer represent the most probable address combinations of the entries of the address codebook at the previous lower layer. Experimental results show reconstructed images at bit rates of 0.5-0.6 bit per pixel with SNR (signal/noise ratio)=28-31 dB. The resulting bit rate is less than that of a standard VQ coding technique by at least a factor of two.>

An interframe coding scheme for the transmission of image sequences at bit rates below 0.2 bits per pixel is presented. The proposed scheme is called an interframe hierarchical (quadtree) vector quantizer. A regular decomposition quadtree method is used to segment the interframe differential signal into homogeneous regions of different block size. Small blocks representing high-contrast moving boundaries known as the impulsive component of the difference signal are vector-quantized. Large blocks typically representing smooth regions of the image are encoded by the local sample mean of the region. Experimental results are presented, confirming that the system can encode image sequence scenes at bit rates below 0.2 bit per pixel per frame. A comparison of the interframe hierarchical vector quantization system and an interframe mean reconstructed quadtree method is presented.>